Catégorie AI BENCHY
Classement Combiné
Voyez quels modèles d'IA réussissent le mieux sur Combiné, lesquels restent fiables et où les écarts sont les plus marqués. Trier par: Tests corrects ↓.
| Rang | Modèle | Entreprise | Score Combiné | Score | Tests corrects | Temps de réponse (moy.) |
|---|---|---|---|---|---|---|
| #17 | GLM 5 medium | Z.ai | 10.0 | 8.3 | 1/1 | 29.0s |
| #18 | Qwen3.7 Plus medium | Qwen | 10.0 | 8.2 | 1/1 | 65.2s |
| #19 | Seed-2.0-Lite medium | Bytedance Seed | 10.0 | 8.2 | 1/1 | 37.7s |
| #21 | GPT-5.4 medium | OpenAI | 10.0 | 8.0 | 1/1 | 20.6s |
| #22 | Step 3.7 Flash medium | Stepfun | 10.0 | 8.0 | 1/1 | 9.06s |
| #23 | GLM 5 Turbo medium | Z.ai | 10.0 | 8.0 | 1/1 | 13.9s |
| #24 | GPT-5.2 Chat none | OpenAI | 10.0 | 7.9 | 1/1 | 9.12s |
| #25 | Qwen3.5 Plus 2026-02-15 medium | Qwen | 10.0 | 7.9 | 1/1 | 46.8s |
| #26 | Qwen3.6 Plus medium | Qwen | 10.0 | 7.9 | 1/1 | 35.0s |
| #28 | Gemini 2.5 Flash medium | 10.0 | 7.8 | 1/1 | 28.4s | |
| #29 | Qwen3.5-122B-A10B medium | Qwen | 10.0 | 7.8 | 1/1 | 107.8s |
| #30 | Qwen3.5-27B medium | Qwen | 10.0 | 7.8 | 1/1 | 164.0s |
| #31 | DeepSeek V4 Flash high | DeepSeek | 10.0 | 7.7 | 1/1 | 76.6s |
| #33 | Hy3 preview medium | Tencent | 10.0 | 7.7 | 1/1 | 46.0s |
| #36 | Qwen3.5 Plus 2026-04-20 medium | Qwen | 10.0 | 7.6 | 1/1 | 92.4s |